From c03f4eb8fd1d32ea778bf61f6a2350dd84900dde Mon Sep 17 00:00:00 2001
From: ModelHub XC <noreply@modelhub.org.cn>
Date: Tue, 25 Aug 2026 00:55:17 +0800
Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?=
 =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?=
 =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Model: Likithp/v10_gemma3_1B_rand_s42
Source: Original Platform
---
 .gitattributes                 |  36 ++++++
 README.md                      | 199 +++++++++++++++++++++++++++++++++
 config.json                    |  72 ++++++++++++
 epoch_1/config.json            |  72 ++++++++++++
 epoch_1/epoch_meta.json        |   5 +
 epoch_1/generation_config.json |  13 +++
 epoch_1/model.safetensors      |   3 +
 epoch_1/tokenizer.json         |   3 +
 epoch_1/tokenizer_config.json  |  24 ++++
 epoch_2/config.json            |  72 ++++++++++++
 epoch_2/epoch_meta.json        |   5 +
 epoch_2/generation_config.json |  13 +++
 epoch_2/model.safetensors      |   3 +
 epoch_2/tokenizer.json         |   3 +
 epoch_2/tokenizer_config.json  |  24 ++++
 epoch_3/config.json            |  72 ++++++++++++
 epoch_3/epoch_meta.json        |   5 +
 epoch_3/generation_config.json |  13 +++
 epoch_3/model.safetensors      |   3 +
 epoch_3/tokenizer.json         |   3 +
 epoch_3/tokenizer_config.json  |  24 ++++
 generation_config.json         |  13 +++
 model.safetensors              |   3 +
 tokenizer.json                 |   3 +
 tokenizer_config.json          |  24 ++++
 training_config.json           | 188 +++++++++++++++++++++++++++++++
 26 files changed, 898 insertions(+)
 create mode 100644 .gitattributes
 create mode 100644 README.md
 create mode 100644 config.json
 create mode 100644 epoch_1/config.json
 create mode 100644 epoch_1/epoch_meta.json
 create mode 100644 epoch_1/generation_config.json
 create mode 100644 epoch_1/model.safetensors
 create mode 100644 epoch_1/tokenizer.json
 create mode 100644 epoch_1/tokenizer_config.json
 create mode 100644 epoch_2/config.json
 create mode 100644 epoch_2/epoch_meta.json
 create mode 100644 epoch_2/generation_config.json
 create mode 100644 epoch_2/model.safetensors
 create mode 100644 epoch_2/tokenizer.json
 create mode 100644 epoch_2/tokenizer_config.json
 create mode 100644 epoch_3/config.json
 create mode 100644 epoch_3/epoch_meta.json
 create mode 100644 epoch_3/generation_config.json
 create mode 100644 epoch_3/model.safetensors
 create mode 100644 epoch_3/tokenizer.json
 create mode 100644 epoch_3/tokenizer_config.json
 create mode 100644 generation_config.json
 create mode 100644 model.safetensors
 create mode 100644 tokenizer.json
 create mode 100644 tokenizer_config.json
 create mode 100644 training_config.json

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..bc5f30d
--- /dev/null
+++ b/README.md
@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..cacf532
--- /dev/null
+++ b/config.json
@@ -0,0 +1,72 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.2",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}
diff --git a/epoch_1/config.json b/epoch_1/config.json
new file mode 100644
index 0000000..cacf532
--- /dev/null
+++ b/epoch_1/config.json
@@ -0,0 +1,72 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.2",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}
diff --git a/epoch_1/epoch_meta.json b/epoch_1/epoch_meta.json
new file mode 100644
index 0000000..d99d3fd
--- /dev/null
+++ b/epoch_1/epoch_meta.json
@@ -0,0 +1,5 @@
+{
+  "epoch": 1,
+  "val_em": 0.066,
+  "loss": 0.111812
+}
\ No newline at end of file
diff --git a/epoch_1/generation_config.json b/epoch_1/generation_config.json
new file mode 100644
index 0000000..970986d
--- /dev/null
+++ b/epoch_1/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.10.2"
+}
diff --git a/epoch_1/model.safetensors b/epoch_1/model.safetensors
new file mode 100644
index 0000000..50f0091
--- /dev/null
+++ b/epoch_1/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6377c4db5ebb0a9f543605c993e95bacb2c39aec55e2ab328b87511051b1b51f
+size 1999811208
diff --git a/epoch_1/tokenizer.json b/epoch_1/tokenizer.json
new file mode 100644
index 0000000..f74d183
--- /dev/null
+++ b/epoch_1/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567
diff --git a/epoch_1/tokenizer_config.json b/epoch_1/tokenizer_config.json
new file mode 100644
index 0000000..d4698c9
--- /dev/null
+++ b/epoch_1/tokenizer_config.json
@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/epoch_2/config.json b/epoch_2/config.json
new file mode 100644
index 0000000..cacf532
--- /dev/null
+++ b/epoch_2/config.json
@@ -0,0 +1,72 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.2",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}
diff --git a/epoch_2/epoch_meta.json b/epoch_2/epoch_meta.json
new file mode 100644
index 0000000..0a3c1cc
--- /dev/null
+++ b/epoch_2/epoch_meta.json
@@ -0,0 +1,5 @@
+{
+  "epoch": 2,
+  "val_em": 0.062,
+  "loss": 0.084193
+}
\ No newline at end of file
diff --git a/epoch_2/generation_config.json b/epoch_2/generation_config.json
new file mode 100644
index 0000000..970986d
--- /dev/null
+++ b/epoch_2/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.10.2"
+}
diff --git a/epoch_2/model.safetensors b/epoch_2/model.safetensors
new file mode 100644
index 0000000..f4888ba
--- /dev/null
+++ b/epoch_2/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ebc0b7723de31cabed9328666a5b0aac437d655f8e4d484890dd77bf1d03929
+size 1999811208
diff --git a/epoch_2/tokenizer.json b/epoch_2/tokenizer.json
new file mode 100644
index 0000000..f74d183
--- /dev/null
+++ b/epoch_2/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567
diff --git a/epoch_2/tokenizer_config.json b/epoch_2/tokenizer_config.json
new file mode 100644
index 0000000..d4698c9
--- /dev/null
+++ b/epoch_2/tokenizer_config.json
@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/epoch_3/config.json b/epoch_3/config.json
new file mode 100644
index 0000000..cacf532
--- /dev/null
+++ b/epoch_3/config.json
@@ -0,0 +1,72 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.2",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}
diff --git a/epoch_3/epoch_meta.json b/epoch_3/epoch_meta.json
new file mode 100644
index 0000000..0803cc0
--- /dev/null
+++ b/epoch_3/epoch_meta.json
@@ -0,0 +1,5 @@
+{
+  "epoch": 3,
+  "val_em": 0.064,
+  "loss": 0.083617
+}
\ No newline at end of file
diff --git a/epoch_3/generation_config.json b/epoch_3/generation_config.json
new file mode 100644
index 0000000..970986d
--- /dev/null
+++ b/epoch_3/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.10.2"
+}
diff --git a/epoch_3/model.safetensors b/epoch_3/model.safetensors
new file mode 100644
index 0000000..eea0d2b
--- /dev/null
+++ b/epoch_3/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe08b9b786f2648e0ac03368383a2d96c18a2965d73437737a3684c5cd46309
+size 1999811208
diff --git a/epoch_3/tokenizer.json b/epoch_3/tokenizer.json
new file mode 100644
index 0000000..f74d183
--- /dev/null
+++ b/epoch_3/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567
diff --git a/epoch_3/tokenizer_config.json b/epoch_3/tokenizer_config.json
new file mode 100644
index 0000000..d4698c9
--- /dev/null
+++ b/epoch_3/tokenizer_config.json
@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..970986d
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.10.2"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..eea0d2b
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe08b9b786f2648e0ac03368383a2d96c18a2965d73437737a3684c5cd46309
+size 1999811208
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..f74d183
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..7eb12f9
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,24 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}
diff --git a/training_config.json b/training_config.json
new file mode 100644
index 0000000..e065d21
--- /dev/null
+++ b/training_config.json
@@ -0,0 +1,188 @@
+{
+  "model_family": "gemma3-1b",
+  "mode": "rand",
+  "seed": 42,
+  "hf_repo": "Likithp/v10_gemma3_1B_rand_s42",
+  "base_model": "google/gemma-3-1b-pt",
+  "attn_implementation": "sdpa",
+  "dataset": "data/cs7_rand_v3",
+  "dataset_version": "cs7_v3",
+  "trained_at": "2026-06-07T10:12:07.619317+00:00",
+  "optimizer": "AdamW",
+  "lr": 3e-05,
+  "weight_decay": 0.0,
+  "batch_size": 8,
+  "grad_accum": 8,
+  "effective_batch": 64,
+  "epochs": 3,
+  "warmup_steps": 200,
+  "grad_clip": 0.5,
+  "lr_schedule": "cosine",
+  "checkpoint_criterion": "train_loss",
+  "max_seq_len": 256,
+  "dtype": "torch.bfloat16",
+  "eval_method": "teacher_forcing_argmax",
+  "alias_groups_gemma": {
+    "T1": [
+      "act",
+      "emp",
+      "inv",
+      "ord",
+      "spl",
+      "txn",
+      "empl"
+    ],
+    "T2": [
+      "cst",
+      "brc",
+      "ctg",
+      "dpt",
+      "ordr",
+      "prd",
+      "prj",
+      "rgn",
+      "shp",
+      "tsk",
+      "whs"
+    ]
+  },
+  "note_t1_t2": "empl=T1 and cst=T2 in Gemma tokenizer (reversed vs Qwen)",
+  "log_every_steps": 50,
+  "eval_n": 500,
+  "dry_run": false,
+  "best_epoch": 3,
+  "best_train_loss": 0.083617,
+  "val_exact_match": 0.062,
+  "val_outer_alias_acc": 1.0,
+  "val_inner_alias_acc": 0.059,
+  "val_t1_inner_alias_acc": 0.005348,
+  "val_t2_inner_alias_acc": 0.091054,
+  "val_t1_t2_gap_pp": -8.57,
+  "val_inner_by_alias": {
+    "act": {
+      "correct": 0,
+      "total": 61,
+      "pct": 0.0,
+      "token_group_gemma": "T1"
+    },
+    "brc": {
+      "correct": 0,
+      "total": 50,
+      "pct": 0.0,
+      "token_group_gemma": "T2"
+    },
+    "cst": {
+      "correct": 53,
+      "total": 62,
+      "pct": 85.5,
+      "token_group_gemma": "T2"
+    },
+    "ctg": {
+      "correct": 3,
+      "total": 58,
+      "pct": 5.2,
+      "token_group_gemma": "T2"
+    },
+    "dpt": {
+      "correct": 0,
+      "total": 47,
+      "pct": 0.0,
+      "token_group_gemma": "T2"
+    },
+    "emp": {
+      "correct": 0,
+      "total": 40,
+      "pct": 0.0,
+      "token_group_gemma": "T1"
+    },
+    "empl": {
+      "correct": 0,
+      "total": 43,
+      "pct": 0.0,
+      "token_group_gemma": "T1"
+    },
+    "inv": {
+      "correct": 0,
+      "total": 56,
+      "pct": 0.0,
+      "token_group_gemma": "T1"
+    },
+    "ord": {
+      "correct": 2,
+      "total": 47,
+      "pct": 4.3,
+      "token_group_gemma": "T1"
+    },
+    "ordr": {
+      "correct": 0,
+      "total": 50,
+      "pct": 0.0,
+      "token_group_gemma": "T2"
+    },
+    "prd": {
+      "correct": 1,
+      "total": 55,
+      "pct": 1.8,
+      "token_group_gemma": "T2"
+    },
+    "prj": {
+      "correct": 0,
+      "total": 65,
+      "pct": 0.0,
+      "token_group_gemma": "T2"
+    },
+    "rgn": {
+      "correct": 0,
+      "total": 64,
+      "pct": 0.0,
+      "token_group_gemma": "T2"
+    },
+    "shp": {
+      "correct": 0,
+      "total": 59,
+      "pct": 0.0,
+      "token_group_gemma": "T2"
+    },
+    "spl": {
+      "correct": 0,
+      "total": 56,
+      "pct": 0.0,
+      "token_group_gemma": "T1"
+    },
+    "tsk": {
+      "correct": 0,
+      "total": 59,
+      "pct": 0.0,
+      "token_group_gemma": "T2"
+    },
+    "txn": {
+      "correct": 0,
+      "total": 71,
+      "pct": 0.0,
+      "token_group_gemma": "T1"
+    },
+    "whs": {
+      "correct": 0,
+      "total": 57,
+      "pct": 0.0,
+      "token_group_gemma": "T2"
+    }
+  },
+  "train_log": [
+    {
+      "epoch": 1,
+      "loss": 0.111812,
+      "val_em": 0.066
+    },
+    {
+      "epoch": 2,
+      "loss": 0.084193,
+      "val_em": 0.062
+    },
+    {
+      "epoch": 3,
+      "loss": 0.083617,
+      "val_em": 0.064
+    }
+  ]
+}
\ No newline at end of file